mlsanityData to 7 Oct 2026

Planning from Pixels using Inverse Dynamics Models

arXiv 2012.02419 ↗First posted 4 Dec 2020cs.LG cs.AIcited by 36

Not on the map. Why?

Abstract (arXiv)

Learning task-agnostic dynamics models in high-dimensional observation spaces can be challenging for model-based RL agents. We propose a novel way to learn latent world models by learning to predict sequences of future actions conditioned on task completion. These task-conditioned models adaptively focus modeling capacity on task-relevant dynamics, while simultaneously serving as an effective heuristic for planning with sparse rewards. We evaluate our method on challenging visual goal completion tasks and show a substantial increase in performance compared to prior model-free approaches.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 6; 2023: 13; 2024: 6; 2025: 3; 2026: 3.

36 papers.

Sort:

By area:

  1. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  2. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 636
  3. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 241
  4. 2023STEVE-1: A Generative Model for Text-to-Behavior in Minecraftcited by 95
  5. 2025A Comprehensive Survey on World Models for Embodied AIcited by 65
  6. 2022You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environmentscited by 62
  7. 2022Dichotomy of Control: Separating What You Can Control from What You Cannotcited by 47
  8. 2023World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challengescited by 35
  9. 2023Beyond Reward: Offline Preference-guided Policy Optimizationcited by 35
  10. 2023Emergent Agentic Transformer from Chain of Hindsight Experiencecited by 33
  11. 2021Provable RL with Exogenous Distractors via Multistep Inverse Dynamicscited by 28
  12. 2024Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of Viewcited by 26
24 more
  1. 2023SMORE: Score Models for Offline Goal-Conditioned Reinforcement Learningcited by 21
  2. 2022Imitating Past Successes can be Very Suboptimalcited by 20
  3. 2023Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Datacited by 19
  4. 2022Agent-Controller Representations: Principled Offline RL with Rich Exogenous Informationcited by 15
  5. 2026Latent Geometry Beyond Search: Amortizing Planning in World Modelscited by 13
  6. 2021Learning Domain Invariant Representations in Goal-conditioned Block MDPscited by 12
  7. 2022Bilinear value networkscited by 9
  8. 2023Planning with Sequence Models through Iterative Energy Minimizationcited by 8
  9. 2023Uncertainty-Aware Decision Transformer for Stochastic Driving Environmentscited by 8
  10. 2024PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation Learningcited by 8
  11. 2026INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Modelscited by 7
  12. 2025Adapting a World Model for Trajectory Following in a 3D Gamecited by 5
  13. 2021Planning from Pixels in Environments with Combinatorially Hard Search Spacescited by 4
  14. 2023Reinforcement Learning with Exogenous States and Rewardscited by 4
  15. 2023PcLast: Discovering Plannable Continuous Latent Statescited by 4
  16. 2024Adversarially Robust Decision Transformercited by 4
  17. 2023Language Decision Transformers with Exponential Tilt for Interactive Text Environmentscited by 3
  18. 2024MOOSS: Mask-Enhanced Temporal Contrastive Learning for Smooth State Evolution in Visual Reinforcement Learningcited by 3
  19. 2026LeFlow: Generative Latent Flow Planning for World Modelscited by 3
  20. 2023Discovering Object-Centric Generalized Value Functions From Pixelscited by 1
  21. 2023Deep Generative Models for Decision-Making and Controlcited by 1
  22. 2024MGDA: Model-based Goal Data Augmentation for Offline Goal-conditioned Weighted Supervised Learningcited by 1
  23. 2025Bridging the Gap Between Multimodal Foundation Models and World Modelscited by 1
  24. 2024Transformers and Slot Encoding for Sample Efficient Physical World Modellingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning
  2. 2026FIRM-WM: State-factorized factual-interventional recurrent modeling for reward-free visual planning
  3. 2020World Model as a Graph: Learning Latent Landmarks for Planning
  4. 2018Learning Latent Dynamics for Planning from Pixels
  5. 2026Hierarchical Planning with Latent World Models
  6. 2026Back to Parsimonious Latents: Learning Task-Centric World Models from Visual Foundations
  7. 2026The Planning Limits of Latent World Models
  8. 2026ACID: Action Consistency via Inverse Dynamics for Planning with World Models